© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2003
    Prev
    Next
    INDEX
    Explanations

    python libraries: pygame, matplotlib, scikit, pandas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç½ļ
    -0.27
    hte
    -0.25
    åIJĦåĽ½
    -0.23
     Cypress
    -0.23
     flo
    -0.23
     rơi
    -0.22
    äºļ太
    -0.22
    æĥħ
    -0.22
     ALOG
    -0.22
     ves
    -0.21
    POSITIVE LOGITS
    Handles
    0.27
    handles
    0.26
     Python
    0.25
    æŁĦ
    0.24
     python
    0.24
    Python
    0.24
    python
    0.24
    tutorial
    0.23
    /python
    0.23
     ORM
    0.22
    Activations Density 0.360%

    No Known Activations